Compare AI models

Specifications
Parameters
—9B/32B
Context window
1M128k
API pricing
Input price
$2.00$0.1032B checkpoint
Output price
$8.00$0.10
Cached input price
$0.50—
Cheapest input
$2.00Azure—
Cheapest output
$8.00Azure—
$800OpenAI list price$25.00Z.ai list price
Benchmarks
SWE-Bench Verified
54.6%27.2%
IFEval
87.4%87.6%
Overview
CompanyOpenAIZ.ai
Release dateApr 14 2025Apr 14 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4.1 and GLM-4-0414 are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, IFEval). GLM-4-0414 is cheaper on both input and output: $0.10 vs $2.00 per million input tokens, and $0.10 vs $8.00 per million output tokens. The listed GLM-4-0414 rates use the “32B checkpoint” pricing scope. Both models were released on the same day — Apr 14 2025.

Context windows are 1M (GPT-4.1) vs 128k (GLM-4-0414). GPT-4.1 is closed, while GLM-4-0414 is open weight.

On SWE-Bench Verified, GPT-4.1 leads at 54.6% vs GLM-4-0414 at 27.2%. On IFEval, GLM-4-0414 leads at 87.6% vs GPT-4.1 at 87.4%.